{"id":"https://openalex.org/W2115153654","doi":"https://doi.org/10.1109/tai.2003.1250207","title":"Reinforcement learning with extended spatial and temporal learning scale","display_name":"Reinforcement learning with extended spatial and temporal learning scale","publication_year":2004,"publication_date":"2004-03-02","ids":{"openalex":"https://openalex.org/W2115153654","doi":"https://doi.org/10.1109/tai.2003.1250207","mag":"2115153654"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2003.1250207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2003.1250207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 15th IEEE International Conference on Tools with Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008999201","display_name":"Xiaodong Zhuang","orcid":"https://orcid.org/0000-0001-6508-8507"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaodong Zhuang","raw_affiliation_strings":["Computer Science Department, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qingchum Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingchum Meng","raw_affiliation_strings":["Computer Science Department, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100727286","display_name":"Bo Yin","orcid":"https://orcid.org/0000-0001-6318-0174"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yin","raw_affiliation_strings":["Computer Science Department, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008999201"],"corresponding_institution_ids":["https://openalex.org/I59028903"],"apc_list":null,"apc_paid":null,"fwci":0.4626,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7636569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"324","last_page":"328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8964134454727173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6457473635673523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6318869590759277},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.6164736747741699},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5919499397277832},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5799750089645386},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47305384278297424},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.46616891026496887},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4276476502418518},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2862265110015869},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.1777241826057434}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8964134454727173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6457473635673523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6318869590759277},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.6164736747741699},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5919499397277832},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5799750089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47305384278297424},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.46616891026496887},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4276476502418518},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2862265110015869},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.1777241826057434},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2003.1250207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2003.1250207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 15th IEEE International Conference on Tools with Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W790997768","https://openalex.org/W1610678877","https://openalex.org/W2042243448","https://openalex.org/W2107726111","https://openalex.org/W2297395784","https://openalex.org/W2347363130","https://openalex.org/W3143073527","https://openalex.org/W6697634807"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2130711276","https://openalex.org/W4321463377","https://openalex.org/W3148138296","https://openalex.org/W1528400370","https://openalex.org/W3153786280","https://openalex.org/W2152445738","https://openalex.org/W3127551068","https://openalex.org/W2610411144","https://openalex.org/W1895652315"],"abstract_inverted_index":{"In":[0,58],"this":[1],"paper,":[2],"extended":[3,67],"learning":[4,16,27,51,56,64,68,89,93],"scale":[5,17,69,90],"is":[6,18,28],"proposed":[7,63],"to":[8],"improve":[9],"the":[10,24,32,35,53,59,62,83,92],"efficiency":[11],"of":[12,26,34,55,85],"reinforcement":[13,50],"learning.":[14],"The":[15,78],"defined":[19],"and":[20,43,87],"its":[21],"impact":[22],"on":[23,31],"performance":[25],"investigated.":[29],"Based":[30],"correlation":[33],"spatial":[36,86],"or":[37],"temporal":[38,88],"neighboring":[39],"states,":[40],"fuzzy":[41],"state":[42],"ant":[44],"colony":[45],"optimization":[46],"are":[47,70],"incorporated":[48],"into":[49],"for":[52],"extension":[54,84],"scale.":[57],"simulation":[60],"experiments,":[61],"methods":[65],"with":[66],"applied":[71],"in":[72],"a":[73],"robot":[74],"path":[75],"planning":[76],"problem.":[77],"experimental":[79],"results":[80],"indicate":[81],"that":[82],"improves":[91],"efficiency.":[94]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}